trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 345,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 95.44927536231884,
      "eval_loss": 0.09570997208356857,
      "eval_rouge1": 72.6601,
      "eval_rouge2": 71.6824,
      "eval_rougeL": 72.6858,
      "eval_rougeLsum": 72.4668,
      "eval_runtime": 12.0064,
      "eval_samples_per_second": 5.747,
      "eval_steps_per_second": 1.499,
      "step": 69
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 92.01449275362319,
      "eval_loss": 0.13447459042072296,
      "eval_rouge1": 75.0063,
      "eval_rouge2": 74.0782,
      "eval_rougeL": 75.0597,
      "eval_rougeLsum": 74.8943,
      "eval_runtime": 11.945,
      "eval_samples_per_second": 5.776,
      "eval_steps_per_second": 1.507,
      "step": 138
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 85.46376811594203,
      "eval_loss": 0.14119356870651245,
      "eval_rouge1": 75.3012,
      "eval_rouge2": 74.5492,
      "eval_rougeL": 75.4246,
      "eval_rougeLsum": 75.324,
      "eval_runtime": 10.9494,
      "eval_samples_per_second": 6.302,
      "eval_steps_per_second": 1.644,
      "step": 207
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 85.04347826086956,
      "eval_loss": 0.10889122635126114,
      "eval_rouge1": 74.8426,
      "eval_rouge2": 74.0317,
      "eval_rougeL": 74.8939,
      "eval_rougeLsum": 74.8128,
      "eval_runtime": 11.2109,
      "eval_samples_per_second": 6.155,
      "eval_steps_per_second": 1.606,
      "step": 276
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 85.31884057971014,
      "eval_loss": 0.12416736036539078,
      "eval_rouge1": 75.3806,
      "eval_rouge2": 74.6735,
      "eval_rougeL": 75.5866,
      "eval_rougeLsum": 75.5446,
      "eval_runtime": 11.151,
      "eval_samples_per_second": 6.188,
      "eval_steps_per_second": 1.614,
      "step": 345
    },
    {
      "epoch": 5.0,
      "step": 345,
      "total_flos": 2990604350914560.0,
      "train_loss": 0.036720043679942256,
      "train_runtime": 132.663,
      "train_samples_per_second": 10.402,
      "train_steps_per_second": 2.601
    }
  ],
  "logging_steps": 500,
  "max_steps": 345,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 2990604350914560.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}